I am pleased to announce that our paper titled: “Using Prescriptive Data Analytics to Reduce Grading Bias and Foster Student Success” is accepted for publication at the IEEE Frontiers in Education (FIE) conference 2019 to be held in October 16-19, 2019. This paper was co-authored by Reneta Lansiquot (City Tech) and Christine Rosalia (Hunter College). This is a seminal paper on the topic of reducing grading bias in the classroom by using data analytics. The abstract is as follows:
Abstract: This innovative practice work-in-progress paper presents our approach of using data analytics as an alternative solution to eliminate grading bias. Effective grading involves maintaining consistency among all students, irrespective of gender, race, ethnic background, and prior performance. Related work in this area has shown that prior work submitted by a student influences future scores given. Some of the popular methods used to eliminate grading bias involves grading rubrics, anonymous or blind grading, and/or computerized auto-graders. In spite of all these methods, some types of grading such as essays and projects still require subjective grading, which opens the door to conscious or unconscious bias.
Given the student data available regarding performance, colleges and universities are turning to analytic solutions to extract meaning from huge volumes of student data to help improve retention, graduation, and student performance rates. While looking at all the analytic options can be a daunting task, these analytic options can be categorized at a high level into three distinct types: (a) Descriptive Analytics, which use data aggregation and data mining to provide insight into the past and answer “What has happened?”; (b) Predictive Analytics, which use statistical models and forecasts techniques to understand the future and answer “What could happen?”; and (c) Prescriptive Analytics, which use optimization and simulation algorithms to advise on possible outcomes and answer “What should we do?” In this paper, we use Prescriptive Analytics to provide students with advice on what action to take, based on a tool which predicts each student’s performance.
This entry is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license.
